Özet:

This study, which aims to predict the academic success of the students and to eliminate the missing areas, was applied to the students who took the Introduction to Information Systems Engineering course. It is aimed to increase the quality of education by applying machine learning methods to the effect of the computer knowledge level of these students at the beginning of the semester on the success grade they get at the end of the semester. When the dataset of the students participating in the study was separated as training and test data, meaningless results emerged due to the lack of data. For this reason, "Synthetic Minority Sampling Method (SMOTE)" was chosen as the data multiplication technique in the study to increase the performance of machine learning algorithms. After the data replication process is done, according to the K-nearest neighbor (KNN), Support vector machine (DVM), Logistic Regression (LR), Random Forest (RF), Decision trees (DT) and Naive Bayes machine learning methods applied on the data set. The model created with the nearest neighbor-KNN algorithm gave the best result. This model predicted the classification process of the test data consisting of 300 students independent of the training set, with an accuracy of 97.66%.

Anahtar Kelimeler: